CRMArena - NED — leaderboard
Metric: NED Score (%). Source: huggingface.co. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O1 | 60 |
| 2 | Llama 3.1 70B | 53.8 |
| 3 | Claude 3.5 Sonnet | 52.3 |
| 4 | Llama 3.1 405B | 50 |
| 5 | GPT-4o | 46.2 |
| 6 | DeepSeek R1 | 40.8 |
| 7 | GPT-4o Mini | 31.5 |
| 8 | Claude 3 Sonnet | 30.8 |
| 9 | Llama 3.1 8B | 6.2 |
Interactive version: theaggregate.ai/benchmark?slug=crmarena-ned · How the rankings work · Data refreshed daily, snapshot 2026-07-22.